AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning

Rogério Guimarães, Pietro Perona

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use PSP seed pruning instead of Best-of-N at matched compute N=4SD v1.5 · GenEval promptsGenEval score: 0.542 -> 0.574Improved
use PSP instead of Best-of-N at matched computeSDXL · GenEval promptsGenEval score: 0.629 -> 0.645Improved
use PSP instead of Best-of-N at matched computeSD 3.5 · GenEval promptsGenEval score: 0.747 -> 0.747No clear effect
use PSP instead of Best-of-N, human evaluationSD 3.5 · GenEval prompts human evalhuman prompt-alignment rate: 0.831 -> 0.841Improved
use PSP instead of Best-of-N, human evaluationSDXL · GenEval prompts human evalhuman prompt-alignment rate: 0.682 -> 0.713Improved
use PSP instead of BFS (reward vs prompt alignment)SDXL · GenEval promptsImageReward / GenEval: IR 1.247 -> 1.224; GenEval 0.636 -> 0.645Mixed
apply PSP on DPO-finetuned backbone instead of Best-of-NSD v1.5 DPO · GenEval promptsGenEval score: 0.562 -> 0.593Improved
apply PSP on DPO-finetuned backbone instead of Best-of-NSDXL DPO · GenEval promptsGenEval score: 0.657 -> 0.667Improved
use PSP over prompt rewrites instead of Best-of-N with fixed seedSD v1.5 · GenEval prompts (prompt rewrites)GenEval score: 0.512 -> 0.533Improved
use PSP over prompt rewrites instead of Best-of-N with fixed seedSDXL · GenEval prompts (prompt rewrites)GenEval score: 0.598 -> 0.604Improved
use HPS guidance with PSP instead of Best-of-NSD v1.5 · GenEval prompts (HPS guidance)GenEval score: 0.525 -> 0.541Improved
tune pruning schedule by grid search instead of default halving schedule (IR guidance) (ablation)PSP SDXL · GenEval promptsGenEval score: 0.645 -> 0.641No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy